مدلسازی رفتار سدهای بتنی با استفاده از روشهای شبکه عصبی مصنوعی و رگرسیون لجستیک
محورهای موضوعی : مدیریت آب در مزرعه با هدف بهبود شاخص های مدیریتی آبیاریفردین سعید 1 , محسن ایران دوست 2 , نوید جلال کمالی 3
1 - دانشجوی دکتری، گروه مهندسی آب، واحد کرمان، دانشگاه آزاد اسلامی، کرمان، ایران.
2 - استادیار، گروه مهندسی آب، واحد کرمان، دانشگاه آزاد اسلامی، کرمان، ایران.
3 - استادیار، گروه مهندسی آب، واحد کرمان، دانشگاه آزاد اسلامی، کرمان، ایران.
کلید واژه: الگوریتم بهینهسازی گروه ذرات, تحلیل رگرسیون, سد ستارخان, سد بتنی,
چکیده مقاله :
زمینه و هدف: اندازهگیری و رفتارسنجی سد موضوع جدیدی میباشد که میتواند به دلیل تغییر پارامترهای موجود برای ارائه مدلی باشد که رفتار پارامترهای منفرد را بر روی سد و همچنین روی یکدیگر بررسی کند و تغییرات ایجاد شده را آنالیز کرده و سیاستهای لازم را ایجاد کند. هدف این پژوهش ایجاد یک روش ترکیبی از رگرسیون لجستکی با بهینهسازی الگوریتم بهینهسازی گروه ذرات با مقدار حقیقی جهت پیشبینی رفتار تجهیزات سد میباشد.روش پژوهش: در این مطالعه از دادههای 365 روز، از 31/01/1397 تا 31/01/1398 که 600 مجموعه داده تجهیزات سد شامل پارامترهای دمای آب، سطح آب، فشار دریچه، میزان رسوبگذاری، فشار منافذ، دمای هوا، حجم آب ورودی، مشخصات ویژه سد، شرایط بتن، سطح آب مخزن، تغییر مکان افقی و عمودی، اجزای اتصال انتقالی و شتاب زمین، قدرت، فشار، کشش و تنش بالا برای مدلسازی استفاده شدند. برای آموزش مدلسازی الگوریتم بهینهسازی گروه ذرات مقدار حقیقی-رگرسیون لجستیک و 120 مجموعه داده جهت آزمایش استفاده گردید. برای ارزیابی عملکرد روش پیشنهادی، از چهار آماره شامل ضریب تعیین (R2)، ریشه میانگین مربعات خطا (RMSE)، ضریب پراکندگی (SI) و میانگین خطاهای انحرافی (MBE) استفاده گردید.یافتهها: نتایج نشان داد که مدل در پیش بینی فشار پیزومتریک در بدنه سد عملکرد قابل قبولی دارد. همچنین نتایج حاصل از مدل شبکه عصبی مصنوعی با کسب 930/0 R2= و 587/8SI= همگرایی قابل قبولی را نشان می دهد. نتایج مربوط به دادههای آموزش مدل نیز بیانگر این است که میانگین (µ) و انحراف معیار (σ) مدل ارائه شده، برای داده های آموزش به ترتیب برابر با 341/1 و 526/1 میباشد و برای داده های صحتسنجی این مقادیر برابر با 576/1 و 247/2 می باشد که این نشان از عملکرد خوب مدل پیشنهاد شده دارد. در معیار احتمال تجمعی، مدل پیشنهاد شده با 940/0P50= و 742/1P90= مبین این است که نتایج قابل قبول می باشد.نتایج: نتایج بیانگر این است که بهینهسازی گروه ذرات مقدار حقیقی-رگرسیون لجستیک در عوض به حداقل رساندن ریسک تجربی که تعمیم عالی برای اندازههای نمونه کوچک را فراهم میسازد، اصل کاهش ریسک سازهای را اجرا میکند. نسبت مقادیر پیزومتریک پیشبینیشده به مقادیر قرائتشده برای حدود 72 درصد دادهها در این مدل در حدود یک بوده که بیانگر آموزش و قدرت پیشبینی مناسب این مدل میباشد. در نهایت بر اساس معیارهای ارزیابی مدل ترکیبی عملکرد بهتری نسبت به روشهای بیان شده دارد.
Background and Aim: Dam measurement and behavior assessment is a new issue that can be due to changes in available parameters to develop a model examining the behavior of individual parameters on the dam as well as on each other and analyze the changes and create the necessary policies. This study aims to propose a hybrid method involving logistic regression with particle swarm optimization algorithm with real value to predict the behavior of dam equipment.Method: In this study, from 365 days data, from 04/20/2018 to 04/20/2019, of which 600 sets of dam equipment data including parameters of water temperature, water level, valve pressure, sedimentation rate, pore pressure, air temperature, inlet water volume, specific dam characteristics, concrete conditions, reservoir water level, horizontal and vertical displacement, transmission connection components and ground acceleration, strength, pressure, tensile and high stress were used for modeling. Real value-logistic regression and 120 datasets were used for modeling the should be added of particle group optimization algorithm. To evaluate the performance of the proposed method, four statistics including coefficient of determination (R2), root mean square error (RMSE), scattering coefficient (SI), and means bias error (MBE) were used.Findings: The results showed that the model has an acceptable performance in predicting piezometric pressure in the dam body. Also, the results of the artificial neural network model show acceptable convergence with R2 = 0.930 and SSI = 8.587. The results related to the training data of the model also indicate that the mean (µ) and standard deviation (σ) of the proposed model are equal to 1.341 and 1.526 for the training data and these values for the validation data are equal to 1.576 and 2.247, respectively indicating the good performance of the proposed model. In the cumulative probability criterion, the proposed model with P50 = 0.940 and P90 = 1.742 indicates that the results are acceptable.Results: The results indicate that the real value-logistic regression particle swarm optimization implements the principle of structural risk reduction instead of minimizing the experimental risk that provides excellent generalization for small sample sizes. The ratio of predicted piezometric values to read values for about 72% of the data in this model is about one, indicating the appropriate training and predictive power of this model. Finally, according to the evaluation criteria, the hybrid model performs better than the presented methods.
Acerbi, L., & Ji, W. (2017). Practical Bayesian optimization for model fitting with Bayesian adaptive direct search. In: NIPS'17: Proceedings of the 31st International Conference on Neural Information. Processing Systems, 1834-1844.
Belmokre, A., Mihoubi, M. K., & Santillán, D. (2019). Analysis of dam behavior by statistical models: application of the random forest approach. KSCE Journal of Civil Engineering, 23(11), 4800- 4811.
Chambers, Lance D., ed. (2019). Practical handbook of particle swarm optimization algorithms: complex coding systems (Vol. 3). CRC press.
Chen, S., Gu, C., Lin, C., Zhang, K. & Zhu, Y. (2021). Multi-kernel optimized relevance vector machine for probabilistic prediction of concrete dam displacement. Engineering with Computers, 37(3), 1943-1959.
Colkesen, I., Sahin, E. K. & Kavzoglu, T. (2016). Susceptibility mapping of shallow landslides using kernel based Gaussian process, support vector machines and RPSO. Journal of African Earth Sciences, 118, 53-64.
Colkesen, I., Sahin, E. K., & Kavzoglu, T. (2016). Susceptibility mapping of shallow landslides using kernel-based Gaussian process, support vector machines, and RPSO. Journal of African Ea Sciences, 118, 53-64.
doi: 10.22065/jsce.2020.203517.1957. [in Persian]
Emami, S., Parsa, J., & Emami, H. (2021). Evaluating Cracks in Concrete Dams using Meta-heuristic Algorithms and Artificial Neural Networks. Journal of Structural and Construction Engineering, 8(Special Issue 2).
Feng, J., Liu, L., Wu, D., Li, G., Beer, M., & Gao, W. (2019). Dynamic reliability analysis using the extended support vector regression (X-SVM). Mechanical Systems and Signal Processing, 126, 368-391.
Gitoee, A., Faridi, A., & France, J. (2018). Mathematical models for response to amino acids: estimating the response of broiler chickens to branched-chain amino acids using support vector regression and neural network models. Neural Computing and Applications, 30(8), 2499-2508.
Gu, H., Yang, M., Gu, C., Cao, W., Huang, X. & Su, H. (2020). An analytical approach of behavior changes for concrete dam by panel data model. Steel and Composite Structures, 36(5), 521-531.
Han, H. G., Guo, Y. N., & Qiao, J. F. (2018). Nonlinear system modeling using a self-organizing recurrent radial basis function neural network. Applied Soft Computing, 71, 1105-1116.
Hussain, Z. F., Ibraheem, H. R., Alsajri, M., Ali, A. H., Ismail, M. A., Kasim, S., & Sutikno, T. (2020). A new model for iris data set classification based on linear support vector machine parameter optimization. International Journal of Electrical and Computer Engineering, 10(1), 1079-1084.
Kalita, D. J., Singh, V. P., & Kumar, V. (2020). A Survey on Logistic Regression Hyper-Parameters Optimization Techniques. In: Social Networking and Computational Intelligence, Springer, Singapore, 243-256.
Li, D., Wu, Y., Gao, E., Wang, G., Xu, Y., Zhong, H., & Wu, W. (2020). Simulation of Seawater Intrusion Area Using Feedforward Neural Network in Longkou, China. Water, 12(8), 2107. https://doi.org/10.3390/w12082107
Li, M., & Wang, J. (2019). An empirical comparison of multiple linear regression and artificial neural network for concrete dam deformation modeling. Mathematical Problems in Engineering. https://doi.org/10.1155/2019/7620948.
Ma, B., and Xia, Y. (2017). A tribe competition-based particle swarm optimization algorithm for feature selection in pattern classification. Applied Soft Computing, 58, 328-338.
Mata, J., Salazar, F., Barateiro, J., & Antunes, A. (2021). Validation of Machine Learning Models for Structural Dam Behaviour Interpretation and Prediction. Water, 13(19), 2717. https://doi.org/10.3390/w13192717
Nan, F., Ding, R., Nallapati, R., & Xiang, B. (2019). Topic Modeling with Wasserstein Autoencoders. arXiv preprint arXiv:1907.12374.
Neshat, M., Tabatabi, M., Zahmati, E., & Shirdel, M. (2016). A hybrid fuzzy knowledge-based system for forest fire risk forecasting. International Journal of Reasoning-based Intelligent Systems, 8(3-4), 132-154 [In Persian].
Oneto, L., Bisio, F., Cambria, E., & Anguita, D. (2016). Statistical learning theory and ELM for big social data analysis. IEEE Computational Intelligence Magazine, 11(3), 45-55. https://doi.org/10.1109/MCI.2016.2572540
Peng, K. L., Wu, C. H., & Goo, Y. J. (2004). The development of a new statistical technique for relating financial information to stock market returns. International Journal of Management, 21(4), 492-505.
Raj, J. S., & Ananthi, J. V. (2019). Recurrent neural networks and nonlinear prediction in support vector machines. Journal of Soft Computing Paradigm (JSCP), 1(01), 33-40. https://doi.org/10.36548/jscp.2019.1.004
Reis, L. P., de Souza, A. L., dos Reis, P. C. M., Mazzei, L., Soares, C. P. B., Torres, C. M. M. E., da Silva, L. F., Ruschel, A. R., Rêgo, L. J. S. & Leite, H. G. (2018). Estimation of mortality and survival of individual trees after harvesting wood using artificial neural networks in the amazon rain forest. Ecological Engineering, 112, 140-147.
Rong, M., Gong, D., & Gao, X. (2019). Feature selection and its use in big data: challenges, methods and trends. IEEE Access, 7, 19709-19725.
Samigulina, G., & Massimkanova, Z. (2019). Development of Smart-Technology for Forecasting Technical State of Equipment Based on Modified Particle Swarm Algorithms and Immune-Network Modeling. In: International Conference on Computational & Experimental Engineering and Sciences. Springer, Cham, 283-293.
Schratz, P., Muenchow, J., Iturritxa, E., Richter, J., & Brenning, A. (2018). Performance evaluation and hyperparameter tuning of statistical and machine-learning models using spatial data. arXiv preprint arXiv:1803.11266.
Shakarami, L., Javdanian, H., Sanayei, H. R. Z., & Shams, G. (2019). Numerical investigation of seismically induced crest settlement of earth dams. Modeling Earth Systems and Environment, 5(4), 1231-1238.
Siniscalchi, S. M., & Salerno, V. M. 2016. Adaptation to new microphones using artificial neural networks with trainable activation functions. IEEE transactions on neural networks and learn systems, 28(8), 1959-1965. https://doi.org/10.1109/TNNLS.2016.2550532.
_||_
Acerbi, L., & Ji, W. (2017). Practical Bayesian optimization for model fitting with Bayesian adaptive direct search. In: NIPS'17: Proceedings of the 31st International Conference on Neural Information. Processing Systems, 1834-1844.
Belmokre, A., Mihoubi, M. K., & Santillán, D. (2019). Analysis of dam behavior by statistical models: application of the random forest approach. KSCE Journal of Civil Engineering, 23(11), 4800- 4811.
Chambers, Lance D., ed. (2019). Practical handbook of particle swarm optimization algorithms: complex coding systems (Vol. 3). CRC press.
Chen, S., Gu, C., Lin, C., Zhang, K. & Zhu, Y. (2021). Multi-kernel optimized relevance vector machine for probabilistic prediction of concrete dam displacement. Engineering with Computers, 37(3), 1943-1959.
Colkesen, I., Sahin, E. K. & Kavzoglu, T. (2016). Susceptibility mapping of shallow landslides using kernel based Gaussian process, support vector machines and RPSO. Journal of African Earth Sciences, 118, 53-64.
Colkesen, I., Sahin, E. K., & Kavzoglu, T. (2016). Susceptibility mapping of shallow landslides using kernel-based Gaussian process, support vector machines, and RPSO. Journal of African Ea Sciences, 118, 53-64.
doi: 10.22065/jsce.2020.203517.1957. [in Persian]
Emami, S., Parsa, J., & Emami, H. (2021). Evaluating Cracks in Concrete Dams using Meta-heuristic Algorithms and Artificial Neural Networks. Journal of Structural and Construction Engineering, 8(Special Issue 2).
Feng, J., Liu, L., Wu, D., Li, G., Beer, M., & Gao, W. (2019). Dynamic reliability analysis using the extended support vector regression (X-SVM). Mechanical Systems and Signal Processing, 126, 368-391.
Gitoee, A., Faridi, A., & France, J. (2018). Mathematical models for response to amino acids: estimating the response of broiler chickens to branched-chain amino acids using support vector regression and neural network models. Neural Computing and Applications, 30(8), 2499-2508.
Gu, H., Yang, M., Gu, C., Cao, W., Huang, X. & Su, H. (2020). An analytical approach of behavior changes for concrete dam by panel data model. Steel and Composite Structures, 36(5), 521-531.
Han, H. G., Guo, Y. N., & Qiao, J. F. (2018). Nonlinear system modeling using a self-organizing recurrent radial basis function neural network. Applied Soft Computing, 71, 1105-1116.
Hussain, Z. F., Ibraheem, H. R., Alsajri, M., Ali, A. H., Ismail, M. A., Kasim, S., & Sutikno, T. (2020). A new model for iris data set classification based on linear support vector machine parameter optimization. International Journal of Electrical and Computer Engineering, 10(1), 1079-1084.
Kalita, D. J., Singh, V. P., & Kumar, V. (2020). A Survey on Logistic Regression Hyper-Parameters Optimization Techniques. In: Social Networking and Computational Intelligence, Springer, Singapore, 243-256.
Li, D., Wu, Y., Gao, E., Wang, G., Xu, Y., Zhong, H., & Wu, W. (2020). Simulation of Seawater Intrusion Area Using Feedforward Neural Network in Longkou, China. Water, 12(8), 2107. https://doi.org/10.3390/w12082107
Li, M., & Wang, J. (2019). An empirical comparison of multiple linear regression and artificial neural network for concrete dam deformation modeling. Mathematical Problems in Engineering. https://doi.org/10.1155/2019/7620948.
Ma, B., and Xia, Y. (2017). A tribe competition-based particle swarm optimization algorithm for feature selection in pattern classification. Applied Soft Computing, 58, 328-338.
Mata, J., Salazar, F., Barateiro, J., & Antunes, A. (2021). Validation of Machine Learning Models for Structural Dam Behaviour Interpretation and Prediction. Water, 13(19), 2717. https://doi.org/10.3390/w13192717
Nan, F., Ding, R., Nallapati, R., & Xiang, B. (2019). Topic Modeling with Wasserstein Autoencoders. arXiv preprint arXiv:1907.12374.
Neshat, M., Tabatabi, M., Zahmati, E., & Shirdel, M. (2016). A hybrid fuzzy knowledge-based system for forest fire risk forecasting. International Journal of Reasoning-based Intelligent Systems, 8(3-4), 132-154 [In Persian].
Oneto, L., Bisio, F., Cambria, E., & Anguita, D. (2016). Statistical learning theory and ELM for big social data analysis. IEEE Computational Intelligence Magazine, 11(3), 45-55. https://doi.org/10.1109/MCI.2016.2572540
Peng, K. L., Wu, C. H., & Goo, Y. J. (2004). The development of a new statistical technique for relating financial information to stock market returns. International Journal of Management, 21(4), 492-505.
Raj, J. S., & Ananthi, J. V. (2019). Recurrent neural networks and nonlinear prediction in support vector machines. Journal of Soft Computing Paradigm (JSCP), 1(01), 33-40. https://doi.org/10.36548/jscp.2019.1.004
Reis, L. P., de Souza, A. L., dos Reis, P. C. M., Mazzei, L., Soares, C. P. B., Torres, C. M. M. E., da Silva, L. F., Ruschel, A. R., Rêgo, L. J. S. & Leite, H. G. (2018). Estimation of mortality and survival of individual trees after harvesting wood using artificial neural networks in the amazon rain forest. Ecological Engineering, 112, 140-147.
Rong, M., Gong, D., & Gao, X. (2019). Feature selection and its use in big data: challenges, methods and trends. IEEE Access, 7, 19709-19725.
Samigulina, G., & Massimkanova, Z. (2019). Development of Smart-Technology for Forecasting Technical State of Equipment Based on Modified Particle Swarm Algorithms and Immune-Network Modeling. In: International Conference on Computational & Experimental Engineering and Sciences. Springer, Cham, 283-293.
Schratz, P., Muenchow, J., Iturritxa, E., Richter, J., & Brenning, A. (2018). Performance evaluation and hyperparameter tuning of statistical and machine-learning models using spatial data. arXiv preprint arXiv:1803.11266.
Shakarami, L., Javdanian, H., Sanayei, H. R. Z., & Shams, G. (2019). Numerical investigation of seismically induced crest settlement of earth dams. Modeling Earth Systems and Environment, 5(4), 1231-1238.
Siniscalchi, S. M., & Salerno, V. M. 2016. Adaptation to new microphones using artificial neural networks with trainable activation functions. IEEE transactions on neural networks and learn systems, 28(8), 1959-1965. https://doi.org/10.1109/TNNLS.2016.2550532.